Image Classification Using Color and Spatial Frequency in Terms of Human Emotion
Image classification is helpful for searching and image retrieval in terms of corresponding to the preference of users. However previous works did not consider human emotion but perform the retrieval by using keywords or objects in image. In the field of
- PDF / 1,595,384 Bytes
- 6 Pages / 439.37 x 666.142 pts Page_size
- 64 Downloads / 233 Views
2
Department of Computer Science, Sangmyung University, Seoul, Republic of Korea [email protected], [email protected] Department of Sports ICT Convergence, Sangmyung University, Seoul, Republic of Korea
Abstract. Image classification is helpful for searching and image retrieval in terms of corresponding to the preference of users. However previous works did not consider human emotion but perform the retrieval by using keywords or objects in image. In the field of color psychology, the color has been proven that an impact on the human emotion. Also, visual complexity such as spatial frequency affects to human emotion. In this paper, a new image classification method is proposed for analyzing the relationship between image components such as color and spatial frequency and human emotion. We collected totally 391 images which contained the three different kinds of scene categories such as natural scene, campus scene, and human made scene images from the public image database. Consequently, we confirmed that image can be reasonably classified by using the color and spatial frequency in terms of human emotion. Keywords: Image classification Color Spatial frequency Human emotion
1 Introduction Since the numerous image contents have been widely distributed according to the explosive growth of the Web nowadays, image search and classification has become more popular and important technology as well as growing challenging issues. Image classification is helpful techniques in several ways as follows. Firstly, image classification will be useful method as a convenient user interface for searching the image database in terms of corresponding to the preference of users [1]. Moreover, image clustering can be used for improving the performance and speed of content-based image retrieval (CBIR) [2]. In previous works, many researches have performed for image classification by using color as well as texture characteristics which can be easily extracted from images by using the several clustering algorithms such as k-means, spectral clustering, minimum distances, and decision rules [3]. Color components or texture can be used for identifying regions of interest or objects in images. However, because the many previous image classification methods have performed by using the only one low-level visual feature, researches were rarely presented by © Springer Nature Singapore Pte Ltd. 2017 J.J. (Jong Hyuk) Park et al. (eds.), Advanced Multimedia and Ubiquitous Engineering, Lecture Notes in Electrical Engineering 448, DOI 10.1007/978-981-10-5041-1_16
92
M.W. Park et al.
using the two kinds of visual information. Also, many researches above mentioned were not considered in terms of human emotion, the clustering results cannot be satisfied for people. In other words, these applications were not appropriate for affective computing application. Therefore, standard should be existed for the image classification by considering the human emotion. According to Russell emotion model, human emotion is defined as a twodimensional emotion model for desi
Data Loading...
